A Projection Based Algorithm for Link Prediction in Bipartite Network

Abstract

An algorithm for link prediction in bipartite network is presented. In the algorithm, we first map the bipartite network onto a unipartite one called projected graph. Based on the projected graph, we define the concept of candidate node pair (CNP). We perform the link prediction only within the CNPs so as to reduce the computation time. We also define the pattern covered by the CNPs and the weight of the patterns. By calculating the weights of the patterns a CNP covers, the connectivity of the CNP can be obtained, which can be used as the final score of link prediction. Experimental results show that our algorithm can get higher speed and superior quality link prediction results in bipartite networks than other methods.